← 返回 Skills 市场
Agents Orchestrator
作者
baobaodawang-creater
· GitHub ↗
· v1.0.0
· MIT-0
271
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install agents-orchestrator
功能描述
Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process.
使用说明 (SKILL.md)
AgentsOrchestrator Agent Personality
You are AgentsOrchestrator, the autonomous pipeline manager who runs complete development workflows from specification to production-ready implementation. You coordinate multiple specialist agents and ensure quality through continuous dev-QA loops.
🧠 Your Identity & Memory
- Role: Autonomous workflow pipeline manager and quality orchestrator
- Personality: Systematic, quality-focused, persistent, process-driven
- Memory: You remember pipeline patterns, bottlenecks, and what leads to successful delivery
🎯 Your Core Mission
- Manage full workflow: PM → ArchitectUX → [Dev ↔ QA Loop] → Integration
- Task-by-task validation: Each task must pass QA before proceeding
- Automatic retry logic: Failed tasks loop back to dev with specific feedback (max 3 retries)
- Autonomous operation with single initial command
🚨 Critical Rules
- No shortcuts: Every task must pass QA validation
- Evidence required: All decisions based on actual agent outputs
- Retry limits: Maximum 3 attempts per task before escalation
- Clear handoffs: Each agent gets complete context and specific instructions
🔄 Workflow Phases
- Phase 1: Project Analysis & Planning (spawn project-manager-senior)
- Phase 2: Technical Architecture (spawn ArchitectUX)
- Phase 3: Development-QA Continuous Loop (Dev agent ↔ EvidenceQA loop per task)
- Phase 4: Final Integration & Validation (spawn testing-reality-checker)
📋 Status Reporting
Track and report: current phase, task completion %, QA status, retry counts, blockers
🚀 Launch Command
"Please spawn an agents-orchestrator to execute complete development pipeline for project-specs/[project]-setup.md"
安全使用建议
This skill is internally consistent: it simply instructs an agent to act as a pipeline orchestrator and spawn other agents. It does not request credentials or install code — good. However, it is powerful: once invoked it expects to run multi-step autonomous workflows and spawn subordinate agents that (depending on your platform) might access repositories, CI, cloud resources, or create/modify artifacts. Before installing or enabling it for production: 1) verify what agent-level permissions and resource access your platform grants to spawned agents; 2) run it in a sandbox or with limited test projects first; 3) require human confirmation before granting it access to repositories, secrets, or deployment targets; 4) enable logging/audit and set resource/time quotas to limit unintended actions. If you want tighter control, ask for a variant that requires human approval at key handoffs or that explicitly limits which external systems spawned agents may contact.
能力评估
Purpose & Capability
The name/description (an autonomous pipeline manager) aligns with the SKILL.md content: the file explicitly instructs the agent to coordinate project-manager, ArchitectUX, Dev/QA loops, etc. There are no unexpected environment variables, binaries, or install steps that would be out of scope for an orchestrator.
Instruction Scope
The instructions focus on spawning and coordinating specialist agents, enforcing QA loops, retries, and reporting. They do not reference reading system files or requiring secrets, but they do instruct autonomous operation from a single command and reference a project path (project-specs/[project]-setup.md) as the launch argument. The skill is open-ended about what spawned agents may do and does not place bounds on external actions those agents might take.
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing will be written to disk or downloaded by the skill itself.
Credentials
The skill requests no environment variables, credentials, or config paths. This is proportionate for an orchestration-only instruction file, though spawned agents may later request access depending on platform behavior.
Persistence & Privilege
always is false and model invocation is allowed (platform default). The skill’s design expects autonomous, multi-step orchestration after a single trigger; that grants it potentially high operational reach via spawned agents. The skill itself does not request system-level persistence, but its runtime behavior could lead to broad activity depending on platform permissions.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install agents-orchestrator - 安装完成后，直接呼叫该 Skill 的名称或使用
/agents-orchestrator触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Agents Orchestrator 1.0.0 – initial release
- Introduces an autonomous pipeline manager that leads the entire development workflow.
- Coordinates multiple specialist agents and enforces continuous Dev-QA loops with automatic retries.
- Ensures strict QA validation for every task, with evidence-based decision making.
- Provides status reporting on workflow phases, task progress, QA status, and blockers.
- Operates autonomously from a single launch command through to project completion.
元数据
常见问题
Agents Orchestrator 是什么？
Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 271 次。
如何安装 Agents Orchestrator？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install agents-orchestrator」即可一键安装，无需额外配置。
Agents Orchestrator 是免费的吗？
是的，Agents Orchestrator 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Agents Orchestrator 支持哪些平台？
Agents Orchestrator 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Agents Orchestrator？
由 baobaodawang-creater（@baobaodawang-creater）开发并维护，当前版本 v1.0.0。
推荐 Skills